© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2025
    Prev
    Next
    INDEX
    Explanations

    largely centered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ،
    1.44
    ,
    1.23
    、
    1.07
     ،
    1.04
    credibly
    1.01
    ，
    0.99
    ؛
    0.92
    ‎
    0.91
    மான
    0.90
    #,
    0.89
    POSITIVE LOGITS
     οποίο
    1.30
     которым
    1.20
     which
    1.09
     которой
    1.07
    <unused278>
    1.07
     hvilket
    1.06
     których
    1.06
     sodass
    1.05
     commensurate
    1.04
     surpassing
    1.04
    Activations Density 0.544%

    No Known Activations